Papers Zero-shot 3D classification
“Zero-shot 3D classification” 태그가 달린 논문 16편 · 필터 해제
Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding
Zero-shot recognition models require extensive training data for generalization. However, in zero-shot 3D classification, collecting 3D data and captions is costly and laborintensive, posing a significant barrier compare…
3D ClassificationZero-shot 3D classificationZero-Shot LearningMM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding
We introduce MM-Mixing, a multi-modal mixing alignment framework for 3D understanding. MM-Mixing applies mixing-based methods to multi-modal data, preserving and optimizing cross-modal connections while enhancing diversi…
3D Classification3D Object Recognition3D Shape RetrievalContrastive Learning+6OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images
Recent open-world 3D representation learning methods using Vision-Language Models (VLMs) to align 3D point cloud with image-text information have shown superior 3D zero-shot performance. However, CAD-rendered images for …
Representation LearningTransfer LearningZero-shot 3D classificationZero-shot 3D Point Cloud Classification+3TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding
The limited scale of current 3D shape datasets hinders the advancements in 3D shape understanding, and motivates multi-modal learning approaches which transfer learned knowledge from data-abundant 2D image and language m…
3D Shape RepresentationRepresentation LearningZero-shot 3D classificationZero-shot 3D Point Cloud Classification+2ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM) designed for embodied interaction, exploring a universal 3D object understanding with 3D point clouds and languages. ShapeLLM is built upon…
3D geometry3D Object Captioning3D Point Cloud Classification3D Point Cloud Linear Classification+13MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition
Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize lan…
3D Classification3D Shape RecognitionZero-shot 3D classificationSculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i.e., aligning point cloud representation to image and text embedding space individually. In this paper, we introduce MixCon3D, a …
Contrastive LearningRetrievalText to 3DZero-shot 3D classification+1Uni3D: Exploring Unified 3D Representation at Scale
Scaling up representations for images or text has been extensively investigated in the past few years and has led to revolutions in learning vision and language. However, scalable representation for 3D objects and scenes…
3D Object ClassificationRetrievalZero-shot 3D classificationZero-shot 3D Point Cloud Classification+4ViT-Lens: Initiating Omni-Modal Exploration through 3D Insights
Though the success of CLIP-based training recipes in vision-language models, their scalability to more modalities (e.g., 3D, audio, etc.) is limited to large-scale data, which is expensive or even inapplicable for rare m…
3D ClassificationQuestion AnsweringRepresentation LearningTraining-free 3D Point Cloud Classification+2Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation
In recent years, 3D understanding has turned to 2D vision-language pre-trained models to overcome data scarcity challenges. However, existing methods simply transfer 2D alignment strategies, aligning 3D representations w…
3D Classification3D Part Segmentation3D Point Cloud ClassificationRepresentation Learning+3OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding
We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framework for representation alignment, but wi…
3D Classification3D Shape RepresentationContrastive LearningImage Generation+3ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
Recent advancements in multimodal pre-training have shown promising efficacy in 3D representation learning by aligning multimodal features across 3D shapes, their 2D counterparts, and language descriptions. However, the …
3D Classification3D Point Cloud ClassificationRepresentation LearningText Generation+3ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
The recognition capabilities of current state-of-the-art 3D models are limited by datasets with a small number of annotated data and a pre-defined set of categories. In its 2D counterpart, recent advances have shown that…
3D Architecture3D Classification3D Point Cloud ClassificationClassification+5PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning
Large-scale pre-trained models have shown promising open-world performance for both vision and language tasks. However, their transferred capacity on 3D point clouds is still limited and only constrained to the classific…
3D Classification3D Object Detection3D Open-Vocabulary Instance Segmentation3D Part Segmentation+10CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
Pre-training across 3D vision and language remains under development because of limited training data. Recent works attempt to transfer vision-language pre-training models to 3D vision. PointCLIP converts point cloud dat…
3D Point Cloud ClassificationContrastive LearningFew-Shot LearningPoint Cloud Classification+4PointCLIP: Point Cloud Understanding by CLIP
Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in …
3D Open-Vocabulary Instance SegmentationFew-Shot LearningOpen Vocabulary Object DetectionTraining-free 3D Part Segmentation+5